Improved model predicts ICU readmission and mortality with interpretable results.
problem Lack of clinically interpretable predictions from deep learning models on clinical notes.
method Augmented a convolutional model with an attention mechanism for clinical note prediction.
result Attention mechanism improves prediction performance while providing interpretable results.
The study explores statistical methods to interpret radiological models and identify key features.
problem Interpreting complex radiological models for clinical use.
method Exploration of statistical techniques to assess relationships between radiomic features.
result Identification of key relationships and features for improved interpretability.
Deep learning models interpret patient outcomes better with time aggregation.
problem Chronic ambulatory care data challenges for deep learning models.
method Time-distributed-dense layers combined with GRUs for generalization, clinical interpretation framework.
result Time-distributed-dense layers with GRUs produce the most generalizable models.
SS3M learns disease phenotypes from few labels.
problem Lack of supervised data for disease phenotyping.
method Semi-Supervised Mixed Membership Model (SS3M).
result SS3M learns interpretable disease phenotypes.
Bayesian approach for handling incomplete clinical data.
problem Challenges in machine learning with multimodal, incomplete clinical data.
method Generative and discriminative learning, semi-supervised strategy, imputation of missing views.
result Automatic imputation of missing views and robust inference across different data sources.
AdaCare learns health status from biomarkers across multiple time scales.
problem Lack of explicit extraction of historical biomarker variation and adaptability to diverse patient conditions.
method Scale-adaptive feature extraction and recalibration for interpretability.
result AdaCare achieves state-of-the-art prediction accuracy and provides interpretable results.
AI detects heart disease from ECGs with improved interpretability and performance.
problem Undiagnosed structural heart disease due to high cost and accessibility of echocardiography.
method Generalized additive model integrating clinically meaningful ECG predictors.
result Improved AUROC, AUPRC, and F1 score compared to deep-learning baselines.
Improved 3D ECG feature attributions for clinical interpretation.
problem Lack of interpretability in deep learning models for 12-lead ECG analysis.
method Cross-modal mapping of feature attributions from 12-lead ECG models onto CineECG 3D space.
result Mapped feature attributions yield higher Dice scores than standard 12-lead attributions.
Dynamic CBDT improves treatment effect estimation in clinical data.
problem Estimating heterogeneous treatment effects in observational data with high accuracy and interpretability.
method Dynamic Regularized Causal Boosted Decision Trees (CBDT) integrating variance regularization and calibration.
result Significantly improved estimation accuracy and reliable coverage of true treatment effects.
The paper proposes an interpretable off-policy learning algorithm for medical treatments.
problem Lack of interpretable methods for personalized treatment decisions from observational data.
method Hyperbox search approach for interpretable policies in disjunctive normal form.
result The proposed algorithm outperforms state-of-the-art methods in terms of regret and is rated highly interpretable by clinical experts.
F-GAM improves clinical prediction models for OR outcomes.
problem Limited expressive capability of logistic regression for clinical predictions.
method Factored generalized additive model (F-GAM) that extends GAM with feature interactions.
result F-GAM outperforms other models in AUPRC and AUROC for predicting OR outcomes.
Neural model predicts survival outcomes and reveals feature relationships.
problem Predicting time-to-event outcomes and understanding feature relationships in clinical data.
method Survival and topic modeling combined in a neural network framework.
result Neural survival-supervised topic models achieve competitive accuracy with interpretability.
CoI framework models clinical feature interactions, revealing temporal dependencies and enhancing transparency.
problem Capturing latent, time-varying dependencies among clinical features in time-series data.
method Chain-of-Influence (CoI) framework constructs an explicit, time-unfolded graph of feature interactions.
result Achieves state-of-the-art predictive performance (AUROC of 0.960 on CKD progression and 0.950 on ICU mortality).
Development of interpretable machine learning models for clinical healthcare applications has the potential of changing the way we understand, treat, and ultimately cure, diseases and disorders in many areas of medicine. These models can serve not only as sources of predictions and estimates, but also as discovery tool…
Visual system compares and evaluates machine learning models for clinical data predictions.
problem Challenges in comparing and evaluating different machine learning models for medical predictions.
method Developed a visual analytics system to compare and evaluate multiple models' prediction criteria and consistency.
result Demonstrated the effectiveness of the visual analytics system in assisting clinicians and researchers.
This work proposes a new algorithm for automated and simultaneous phenotyping of multiple co-occurring medical conditions, also referred as comorbidities, using clinical notes from the electronic health records (EHRs). A basic latent factor estimation technique of non-negative matrix factorization (NMF) is augmented wi…
The paper proposes a method to predict the performance of data-driven algorithms using surrogate models.
problem Improving the performance prediction of data-driven knowledge discovery algorithms.
method Surrogate-assisted performance prediction using evolutionary modeling of clinical pathways.
result The proposed approach provides interpretable prediction of algorithm performance and quality.
Bayesian neural network improves ICU patient risk prediction and feature selection.
problem Predicting patient outcomes in ICU with limited interpretability.
method Sparse Bayesian neural network with feature selection.
result Model provides interpretable feature importance for mortality prediction.
Exponential growth in Electronic Healthcare Records (EHR) has resulted in new opportunities and urgent needs for discovery of meaningful data-driven representations and patterns of diseases in Computational Phenotyping research. Deep Learning models have shown superior performance for robust prediction in computational…
Supervised topic models can help clinical researchers find interpretable cooccurence patterns in count data that are relevant for diagnostics. However, standard formulations of supervised Latent Dirichlet Allocation have two problems. First, when documents have many more words than labels, the influence of the labels w…
AI system helps clinicians assess liver metastases quickly and with explanations.
problem Manual assessment of metastases is time-consuming and subjective.
method Interactive AI system with model interpretability.
result AI-assisted assessment improves efficiency and provides explanations.
New method stabilizes deep learning models for clinical risk prediction.
problem Stability issues in deep learning models for clinical risk prediction.
method Bootstrapping-based regularisation framework embedded in deep neural networks.
result Improved prediction stability across multiple datasets.
Improved ECG classification using multi-task learning.
problem Low frequency of rare diagnoses in ECGs.
method Developed a multi-task CNN to classify multiple diagnoses from 12-lead ECGs.
result Adding common classes improves performance on rarer classes.
Hybrid Amortized Inference improves PPG model interpretability.
problem Tension between PPG biomarker accuracy and clinical interpretability.
method Introduces PPGen for biophysical PPG signal-physiological parameter relation, and HAI for fast, robust estimation.
result Hybrid Amortized Inference accurately infers physiological parameters from PPG signals.
New method interprets deep embeddings for diabetes patient clustering.
problem Interpreting deep embeddings for disease progression.
method Patient clustering approach using deep embeddings.
result Clinically meaningful insights into diabetes progression patterns.
Method extracts time-localized clusters to explain deep learning models in ECG analysis.
problem Limited understanding of deep learning models in ECG analysis.
method Extracts time-localized clusters from model's internal representations.
result Enhances trust in AI-driven diagnostics and reveals clinically relevant patterns.
Study predicts blood pressure response to fluid bolus therapy with high accuracy.
problem Predicting successful response to fluid bolus therapy in hypotensive ICU patients.
method Used attention-based LSTM and GRU neural networks on a large ICU database.
result Stacked LSTM with attention mechanism achieved highest accuracy of 0.852.
Analysis of flow cytometry data is an essential tool for clinical diagnosis of hematological and immunological conditions. Current clinical workflows rely on a manual process called gating to classify cells into their canonical types. This dependence on human annotation limits the rate, reproducibility, and complexity …
Study creates a multimodal learning framework for CVD risk prediction.
problem Predicting cardiovascular disease risk in diverse populations.
method Combines cross modal transformers, graph neural networks, and causal representation learning.
result Model predicts personalized CVD risk with causal invariance across subpopulations.
Deep learning predicts ICU mortality with enhanced interpretability.
problem Improving mortality prediction accuracy and clinician trust in AI.
method Trained a deep learning model on MIMIC-III to interpret nursing notes.
result Model reaches ROC of 0.8629, outperforming SAPS-II.
Paper presents an ensemble model for predicting readmission using clinical notes.
problem Limited use of clinical notes in predicting readmission due to their unstructured nature.
method Ensemble model combining vector space modeling and topic modeling.
result Improves readmission prediction by 0.0211 in c-statistics.
New dataset from clinicians improves sepsis prediction models.
problem Circularity in previous sepsis prediction models.
method Developed an independent dataset from clinical judgments, avoiding circularity.
result Achieved state-of-the-art AUROC scores.
AdaptHetero uses MLI to tailor EHR models for subgroup-specific predictions.
problem Lack of subgroup-specific, operationalizable modeling strategies in EHRs.
method Integrates MLI with unsupervised clustering to identify subgroup-specific characteristics.
result Improves predictive performance by up to 174.39 percent across many subpopulations.
Antimicrobial resistance is an important public health concern that has implications in the practice of medicine worldwide. Accurately predicting resistance phenotypes from genome sequences shows great promise in promoting better use of antimicrobial agents, by determining which antibiotics are likely to be effective i…
We developed an automated deep learning system to detect hip fractures from frontal pelvic x-rays, an important and common radiological task. Our system was trained on a decade of clinical x-rays (~53,000 studies) and can be applied to clinical data, automatically excluding inappropriate and technically unsatisfactory …
HRTPP improves TPP interpretability and accuracy in medical event modeling.
problem Lack of interpretability in TPPs for medical event sequences.
method Hybrid-Rule Temporal Point Processes (HRTPP) integrating temporal logic rules and numerical features.
result HRTPP outperforms state-of-the-art interpretable TPPs in predictive performance and clinical interpretability.
Study identifies key aspects of explainable ML for clinical trust.
problem Lack of concrete definitions for usable explanations in clinical settings.
method Surveyed clinicians from two specialties to understand their needs for explainability.
result Characterized specific aspects of explainability that improve trust in ML models.
Study uses image analysis to predict MSI status in tumors.
problem Challenges in distinguishing MSI from its counterpart.
method Interpretable pathological image analysis strategies using Haematoxylin and eosin-stained images.
result Strategies achieve decent performance in MSI prediction.
Study validates machine learning models for patient outcomes using various methods.
problem Validating machine learning models for patient outcomes in electronic health records.
method Used three state-of-the-art machine learning methods (random forest, gradient boosting, logistic regression) to predict patient outcomes and assess feature importance.
result Permutation tests applied to random forest and gradient boosting models showed the most agreement with clinical interpretation of feature importance.
Paper explores using RL to teach ML models what is interpretable to non-technical users.
problem Lack of empirical evidence on what is interpretable to non-technical users.
method Train a neural network to provide risk assessments, then design a RL-based DSS to learn from user interactions.
result ML experts cannot accurately predict what will maximize user confidence in ML models.
DPVis integrates HMMs into visualizations for disease progression analysis.
problem Challenges in interpreting HMMs for disease progression modeling.
method Design study with clinical experts, visualizations of HMM parameters and outcomes.
result DPVis successfully evaluates and summarizes disease progression models.
Disease progression models are instrumental in predicting individual-level health trajectories and understanding disease dynamics. Existing models are capable of providing either accurate predictions of patients prognoses or clinically interpretable representations of disease pathophysiology, but not both. In this pape…
Deep learning analyzes healthcare provider actions and patient outcomes.
problem Understanding provider behavior in non-randomized healthcare settings.
method Deep causal behavioral policy learning (DC-BPL) using transformer architecture.
result Optimal provider policies identified for specific patient types.
Study analyzes how blood pressure impacts cardiac health.
problem Impact of blood pressure on cardiac function.
method Combines deep learning and variational autoencoder for interpretable biomarkers.
result Identifies key factors and patterns of cardiac adaptation.
FedRD improves risk difference estimation in federated learning for clinical outcomes.
problem Privacy-preserving model co-training in medical research is hindered by server-dependent architectures and focus on relative effect measures.
method FedRD is a server-independent, communication-efficient framework for federated risk difference estimation in distributed survival data.
result FedRD provides valid confidence intervals and hypothesis testing, and is asymptotically equivalent to pooled individual-level analysis.
Deep learning predicts heart failure readmission from clinical notes.
problem Predicting and preventing heart failure readmission.
method Convolutional Neural Networks (CNN) trained on clinical notes.
result Deep learning models outperform traditional machine learning methods in readmission prediction.
Stein-Encoder isolates genetic signals in multi-modal biomedical data.
problem Integration of high-dimensional genomic data with clinical data obscures genetic predictive impact.
method White-box supervised framework using Stein's method and residualization.
result Stein-Encoder improves predictive accuracy and reveals specific biological mechanisms.
Study benchmarks machine learning for removing EEG artifacts.
problem Removing artifacts from EEGs to improve clinical interpretation.
method Applied various machine learning algorithms to a large artifact recognition dataset.
result Established a benchmark for future research on artifact removal.